Computer Laboratory

Projects

DPVM: Predicting visible image differences under varying display brightness and viewing distance

Nanyang Ye, Krzysztof Wolski, Rafał K. Mantiuk

IEEE/CVF CVPR 2019

Abstract

Numerous applications require a robust metric that can predict whether image differences are visible or not. However, the accuracy of existing white-box visibility metrics, such as HDR-VDP, is often not good enough. CNN-based black-box visibility metrics have proven to be more accurate, but they cannot account for differences in viewing conditions, such as display brightness and viewing distance. In this paper, we propose a CNN-based visibility metric, which maintains the accuracy of deep network solutions and accounts for viewing conditions. To achieve this, we extend the existing dataset of locally visible differences (LocVis) with a new set of measurements, collected considering aforementioned viewing conditions. Then, we develop a hybrid model that combines white-box processing stages for modeling the effects of luminance masking and contrast sensitivity, with a black-box deep neural network. We demonstrate that the novel hybrid model can handle the change of viewing conditions correctly and outperforms state-of-the-art metrics.

Materials

Publication

Nanyang Ye, Krzysztof Wolski, Rafał K. Mantiuk. Predicting visible image differences under varying display brightness and viewing distance. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019 [BibTex]

Related projects

  • CNN visibility metric - the predecessor of DPVM
  • FovVideoVDP - An image/video quality metric for regular and foveated viewing
  • HDR-VDP - A Visual Difference Predictor for High Dynamic Range Images